powerpc: Reduce footprint of irq_stat

PowerPC is currently using asm-generic/hardirq.h which statically allocates an
NR_CPUS irq_stat array. Switch to an arch specific implementation which uses
per cpu data:

On a kernel with NR_CPUS=1024, this saves quite a lot of memory:

text data bss dec hex filename
8767938 2944132 1636796 13348866 cbb002 vmlinux.baseline
8767779 2944260 1505724 13217763 c9afe3 vmlinux.irq_cpustat

A saving of around 128kB.

Signed-off-by: Anton Blanchard <[e-mail]>
Signed-off-by: Benjamin Herrenschmidt <[e-mail]>

arch/powerpc/include/asm/hardirq.h

···
-#include <asm-generic/hardirq.h>
+#ifndef _ASM_POWERPC_HARDIRQ_H
+#define _ASM_POWERPC_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+
+#define __ARCH_IRQ_STAT
+
+#define local_softirq_pending()	__get_cpu_var(irq_stat).__softirq_pending
+
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq);
+}
+
+#endif /* _ASM_POWERPC_HARDIRQ_H */

arch/powerpc/kernel/irq.c

···
 #define CREATE_TRACE_POINTS
 #include <asm/trace.h>
 
+DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
+EXPORT_PER_CPU_SYMBOL(irq_stat);
+
 int __irq_offset_value;
 static int ppc_spurious_interrupts;